© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 10718
    Prev
    Next
    INDEX
    Explanations

    medical terms associated with renal conditions and patient demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.42
    IVEREF
    -0.36
     CreateTagHelper
    -0.35
    ViewFeatures
    -0.28
    djangoproject
    -0.27
    Developer
    -0.27
    resor
    -0.27
    Organisateur
    -0.26
    adero
    -0.26
    uolo
    -0.26
    POSITIVE LOGITS
     patients
    3.67
     patient
    3.31
     Patients
    3.06
    patients
    2.92
    Patients
    2.92
     pacientes
    2.78
    patient
    2.77
     Patienten
    2.73
    Patient
    2.72
     Patient
    2.70
    Activations Density 1.730%

    No Known Activations